Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/101250
Type: Artigo de evento
Title: Evolutionary Hybrid Composition Of Activation Functions In Feedforward Neural Networks
Author: Iyoda Eduardo Masato
Von Zuben Fernando J.
Abstract: Considering computational algorithms available in the literature, associated with supervised learning in feedforward neural networks, a wide range of distinct approaches can be identified. While the adjustment of the connection weights represents an omnipresent stage, the algorithms differ in three basic aspects: the technique chosen to determined the dimension of the multilayer neural network, the procedure adopted to determine the activation function of each neuron, and the kind of composition of the hidden activations used to produce the output. The advanced learning algorithms are designed to treat all these three aspects during learning, guiding to dedicated solutions. In this paper, an evolutionary hybrid learning algorithm is presented to deal simultaneously with these three aspects. The essence of this approach is the existence of a search procedure based on a synergy between genetic algorithms and conjugate gradient optimization.
Editor: IEEE, United States
Rights: fechado
Identifier DOI: 
Address: http://www.scopus.com/inward/record.url?eid=2-s2.0-0033348949&partnerID=40&md5=348e99e6d2ddb37c4e5a407d489642d3
Date Issue: 1999
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-0033348949.pdf535.79 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.